Forem

# llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Claude Went Down Twice in 48 Hours Last Week. If You Noticed, Your Fallback Failed.
Cover image for Claude Went Down Twice in 48 Hours Last Week. If You Noticed, Your Fallback Failed.

Claude Went Down Twice in 48 Hours Last Week. If You Noticed, Your Fallback Failed.

Comments
8 min read
Part 4 of 4 — Engineering Intent Series : ISL v1.6.2: Evolution for Complex Systems

Part 4 of 4 — Engineering Intent Series : ISL v1.6.2: Evolution for Complex Systems

Comments
6 min read
Cursor 3 Just Shipped a Coding Model Trained From Scratch. Here's Why That Changes the Stack.
Cover image for Cursor 3 Just Shipped a Coding Model Trained From Scratch. Here's Why That Changes the Stack.

Cursor 3 Just Shipped a Coding Model Trained From Scratch. Here's Why That Changes the Stack.

Comments
8 min read
A $10B AI Startup Just Got Breached Through the LLM Library in Your Stack.
Cover image for A $10B AI Startup Just Got Breached Through the LLM Library in Your Stack.

A $10B AI Startup Just Got Breached Through the LLM Library in Your Stack.

Comments
8 min read
Why Your LangChain Agent Keeps Calling the Same Tool in a Loop (and How to Stop It)
Cover image for Why Your LangChain Agent Keeps Calling the Same Tool in a Loop (and How to Stop It)

Why Your LangChain Agent Keeps Calling the Same Tool in a Loop (and How to Stop It)

Comments
7 min read
8 Ways Your LLM App Is Silently Failing Right Now (and What to Instrument for Each)
Cover image for 8 Ways Your LLM App Is Silently Failing Right Now (and What to Instrument for Each)

8 Ways Your LLM App Is Silently Failing Right Now (and What to Instrument for Each)

Comments
6 min read
Datadog Sees the HTTP 200. It Cannot See the Hallucination.
Cover image for Datadog Sees the HTTP 200. It Cannot See the Hallucination.

Datadog Sees the HTTP 200. It Cannot See the Hallucination.

Comments
4 min read
Your First AI Agent in 50 Lines of Python (No Framework, No LangChain)
Cover image for Your First AI Agent in 50 Lines of Python (No Framework, No LangChain)

Your First AI Agent in 50 Lines of Python (No Framework, No LangChain)

Comments
7 min read
OpenTelemetry GenAI Semantic Conventions: Your LLM Traces Should Look Like This in 2026
Cover image for OpenTelemetry GenAI Semantic Conventions: Your LLM Traces Should Look Like This in 2026

OpenTelemetry GenAI Semantic Conventions: Your LLM Traces Should Look Like This in 2026

Comments
5 min read
RAG Is Dead. Long Live RAG.
Cover image for RAG Is Dead. Long Live RAG.

RAG Is Dead. Long Live RAG.

Comments
11 min read
The 5 RAG Failure Modes Nobody Talks About (and How to Detect Them Before Users Do)
Cover image for The 5 RAG Failure Modes Nobody Talks About (and How to Detect Them Before Users Do)

The 5 RAG Failure Modes Nobody Talks About (and How to Detect Them Before Users Do)

Comments
8 min read
Langfuse vs LangSmith vs Phoenix vs Braintrust: The Honest 2026 Comparison
Cover image for Langfuse vs LangSmith vs Phoenix vs Braintrust: The Honest 2026 Comparison

Langfuse vs LangSmith vs Phoenix vs Braintrust: The Honest 2026 Comparison

Comments
5 min read
The Production Readiness Checklist for LLM Apps Nobody Gave You (18 Items)
Cover image for The Production Readiness Checklist for LLM Apps Nobody Gave You (18 Items)

The Production Readiness Checklist for LLM Apps Nobody Gave You (18 Items)

Comments
5 min read
I Built an AI Agent That Fired Itself After 3 Minutes. Here's Why That's a Feature.
Cover image for I Built an AI Agent That Fired Itself After 3 Minutes. Here's Why That's a Feature.

I Built an AI Agent That Fired Itself After 3 Minutes. Here's Why That's a Feature.

Comments
7 min read
LLM-as-Judge: The Eval Technique That Looks Cheap Until It Grades Its Own Bias Back to You
Cover image for LLM-as-Judge: The Eval Technique That Looks Cheap Until It Grades Its Own Bias Back to You

LLM-as-Judge: The Eval Technique That Looks Cheap Until It Grades Its Own Bias Back to You

Comments
7 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.